library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.0     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.1     ✔ tibble    3.2.0
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ purrr     1.0.1     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors
df_amer_air <- read.delim(file='/Users/alessandrobreccia/Desktop/1_ANNO_MAGISTR/2_semester/AdvStat/Lab/Rlab01/american_airline_empl.txt', header=TRUE)
df_delta_air <- read.delim(file='/Users/alessandrobreccia/Desktop/1_ANNO_MAGISTR/2_semester/AdvStat/Lab/Rlab01/delta_airline_empl.txt', header=TRUE)
df_federal_express_air <- read.delim(file='/Users/alessandrobreccia/Desktop/1_ANNO_MAGISTR/2_semester/AdvStat/Lab/Rlab01/federal_express_empl.txt', header=TRUE)
df_united_airline_empl <- read.delim(file='/Users/alessandrobreccia/Desktop/1_ANNO_MAGISTR/2_semester/AdvStat/Lab/Rlab01/united_airline_empl.txt', header=TRUE)

IMPORT AND PROCESSING DATA:

df_amer_air <- df_amer_air %>% add_column(Company="American Airline")
df_delta_air <- df_delta_air %>% add_column(Company="Delta Airline")
df_federal_express_air <- df_federal_express_air %>% add_column(Company="Federal Express Airline")
df_united_airline_empl <- df_united_airline_empl %>% add_column(Company="United Airline") 
df_tot <- full_join(df_amer_air,(full_join(df_delta_air,full_join(df_federal_express_air,df_united_airline_empl))))
## Joining with `by = join_by(Month, Year, Full.time, Part.time, Grand.Total,
## Company)`
## Joining with `by = join_by(Month, Year, Full.time, Part.time, Grand.Total,
## Company)`
## Joining with `by = join_by(Month, Year, Full.time, Part.time, Grand.Total,
## Company)`
df_tot$Full.time <- gsub(',','',df_tot$Full.time) %>% strtoi()
df_tot$Part.time <- gsub(',','',df_tot$Part.time) %>% strtoi()
df_tot$Grand.Total <- gsub(',','',df_tot$Grand.Total) %>% strtoi()
df_tot$date <- as.Date(with(df_tot, paste(Year, Month,1,sep="-")), "%Y-%m-%d")

1.3 : Behaviour of the employees as function of time.

Full Time Employees:

library(tidyverse)
ggplot(data = df_tot, mapping = aes(x = date, y = Full.time)) +
    geom_point(aes(color = Company)) + geom_line(aes(color = Company)) + ggtitle('Full-time employees')

Part Time Employees:

ggplot(data = df_tot, mapping = aes(x = date, y = Part.time)) +
    geom_point(aes(color = Company)) + geom_line(aes(color = Company)) + ggtitle('Part-time employees')

1.4: Maximum and minimum of each company:

companylist <- c('American Airline','Delta Airline','Federal Express Airline','United Airline') 

for(i in 1:4){
      maxemplame <- which.max(df_tot[df_tot$Company == companylist[i],]$Grand.Total) 
      minemplame <- which.min(df_tot[df_tot$Company == companylist[i],]$Grand.Total) 
      
      cat("The maximum number of employees of the", companylist[i] ,"is at", as.character(df_tot[df_tot$Company == companylist[i],]$date[maxemplame]), "and is", df_tot[df_tot$Company == companylist[i],]$Grand.Total[maxemplame], "employees\n" )

      cat("The minimum number of employees of the", companylist[i] ,"is at", as.character(df_tot[df_tot$Company == companylist[i],]$date[maxemplame]), "and is", df_tot[df_tot$Company == companylist[i],]$Grand.Total[maxemplame], "employees\n"  )


}
## The maximum number of employees of the American Airline is at 2018-06-01 and is 109171 employees
## The minimum number of employees of the American Airline is at 2018-06-01 and is 109171 employees
## The maximum number of employees of the Delta Airline is at 2023-01-01 and is 94675 employees
## The minimum number of employees of the Delta Airline is at 2023-01-01 and is 94675 employees
## The maximum number of employees of the Federal Express Airline is at 2021-03-01 and is 270383 employees
## The minimum number of employees of the Federal Express Airline is at 2021-03-01 and is 270383 employees
## The maximum number of employees of the United Airline is at 2001-03-01 and is 102046 employees
## The minimum number of employees of the United Airline is at 2001-03-01 and is 102046 employees

1.5: Fraction of the part-time and full-time worker as function of the year

ggplot(data = df_tot, mapping = aes(x = date, y = Part.time/Grand.Total)) +
    geom_point(aes(color = Company)) + geom_line(aes(color = Company)) + ggtitle('Part-time fraction of employees')

ggplot(data = df_tot, mapping = aes(x = date, y = Full.time/Grand.Total)) +
    geom_point(aes(color = Company)) + geom_line(aes(color = Company)) + ggtitle('Full-time fraction of employees')

1.6: Behaviour of the total number of employees per company around 2020

ggplot(data = subset(df_tot,df_tot$date > '2019-01-01'), mapping = aes(x = date, y = Grand.Total)) +
    geom_point(aes(color = Company)) + geom_line(aes(color = Company)) + ggtitle('Total number of employees ')

We can see in 3 out of 4 companies a clear drop in the total number of employees around the middle of the 2020, right after the beginning of the pandemic.

----------------------Exercise 2 ----------------------

library(nycflights13)
library(tidyverse)
flights$date <- as.Date(with(flights, paste(year, month,day,sep="-")), "%Y-%m-%d")

2.1: Total number of flights departed from the 3 New York City airports

library(dplyr)
flights$wdate <- weekdays(as.Date(flights$date))

totflight <- flights %>%  group_by(date,wdate,origin) %>% summarise(count=n(), .groups='drop')

ggplot(data = totflight, mapping = aes(x = date, y = count)) +
    geom_point(aes(color = origin)) + ggtitle('flights departed from New York City airports')

2.2.1: The average number of flights during the week, compared with the average number of flights during the week end

totflight$week <- strftime(totflight$date, format = "%V")
avgweekend <- totflight[ totflight$wdate == 'Saturday' | totflight$wdate == 'Sunday' , ] %>%  group_by(week) %>% summarise(mean=mean(count),.groups='drop')

avgweek <- totflight[ totflight$wdate == 'Monday' | totflight$wdate == 'Tuesday'  | totflight$wdate == 'Wednesday'  | totflight$wdate == 'Thursday'  | totflight$wdate == 'Friday' ,] %>%  group_by(week) %>% summarise(mean=mean(count),.groups='drop')

avgweekend <- avgweekend %>% add_column(id='week-end')
avgweek <- avgweek %>% add_column(id='week')

avg= rbind(avgweekend,avgweek)

ggplot(data = avg, mapping = aes(x = week, y = mean)) +
    geom_point(aes(color = id)) + ggtitle('Week average and week-end average number of fligths')

2.2.2: Max, Min and average of delay as function of time

library(reshape2)
## 
## Attaching package: 'reshape2'
## The following object is masked from 'package:tidyr':
## 
##     smiths
maxdel <- flights %>%  group_by(date) %>% summarise(max_delay=max(dep_delay, na.rm=TRUE), min_delay=min(dep_delay, na.rm=TRUE), avg_delay=mean(dep_delay, na.rm=TRUE))

maxdel <- melt(maxdel ,  id.vars = 'date', variable.name = 'delays', value.name='minutes' )

ggplot( data=maxdel, mapping = aes(x = date, y = minutes)) + geom_line(aes(color = delays)) + ggtitle('Max, Min and average of delay')

2.3: Average speed of planes divided in companies as function of time

flights$speed <- flights$distance/((flights$air_time %/% 100) + (flights$air_time %% 100)/60)

avgspeed <- flights %>%  group_by(date,origin) %>% summarise(avg=mean(speed, na.rm=TRUE), .groups='drop')

ggplot(data = avgspeed, mapping = aes(x = date, y = avg)) + geom_point(aes(color= origin)) + ggtitle('Average speed of planes')

2.4: Analyzing the offers of the various companies

flights$week <- strftime(flights$date, format = "%V")

perday <- flights %>%  group_by(date,carrier) %>% summarise(flights_per_day=n(), .groups='drop')
perday <- perday %>%  group_by(carrier) %>% summarise(mean_flights_per_day=mean(flights_per_day))

perweek <- flights %>%  group_by(week,carrier) %>% summarise(flights_per_week=n(), .groups='drop')
perweek <- perweek %>%  group_by(carrier) %>% summarise(mean_flights_per_week=mean(flights_per_week))

permonth <- flights %>%  group_by(month,carrier) %>% summarise(flights_per_month=n(), .groups='drop')
permonth <- permonth %>%  group_by(carrier) %>% summarise(mean_flights_per_month=mean(flights_per_month))

distpermoth <- flights %>%  group_by(month,carrier) %>% summarise(dist=max(distance, na.rm=TRUE), .groups='drop')
distpermoth <- distpermoth %>%  group_by(carrier) %>% summarise(mean_dist_per_month=mean(dist))


cat("The company offering the largest number of flights per day is",perday$carrier[which.max(perday$mean_flights_per_day)],"with a value of",perday$mean_flights_per_day[which.max(perday$mean_flights_per_day)],"\n")
## The company offering the largest number of flights per day is UA with a value of 160.726
cat("The company offering the largest number of flights per week is",perweek$carrier[which.max(perweek$mean_flights_per_week)],"with a value of",perweek$mean_flights_per_week[which.max(perweek$mean_flights_per_week)],"\n")
## The company offering the largest number of flights per week is UA with a value of 1128.173
cat("The company offering the largest number of flights per month is",permonth$carrier[which.max(permonth$mean_flights_per_month)],"with a value of",permonth$mean_flights_per_month[which.max(permonth$mean_flights_per_month)],"\n")
## The company offering the largest number of flights per month is UA with a value of 4888.75
cat("The company offering the largest covered distance per month is",distpermoth$carrier[which.max(distpermoth$mean_dist_per_month)],"with a value of",distpermoth$mean_dist_per_month[which.max(distpermoth$mean_dist_per_month)],"\n")
## The company offering the largest covered distance per month is HA with a value of 4983